检索结果-内蒙古大学图书馆

9th International Conference on Future Internet of Things and Cloud, FiCloud 2022

作者： Vrbaski, Mira Bolic, Miodrag Majumdar, Shikharesh University of Ottawa School of Electrical Engineering and Computer Science Ottawa Canada Carleton University Dept. of Systems and Computer Engineering Ottawa Canada

ISBN: (数字)9781665493505

ISBN: (纸本)9781665493505

An approach to optimizing a large-scale microservice deployment for a critical notification system is presented. This paper addresses optimization for three objectives: cloud service cost, cloud resource utilization of CPU, RAM and storage, and meeting the system notification deadlines. To the best of our knowledge, this is the first work dealing with multi-objective optimization for microservice notification applications where the notification load is variable and depends on other priorly executed microservice in request processes. Furthermore, best of our knowledge, this is the first work that is based on multi-objective optimization, analyzing and proposing a Pareto front and optimal list from preselected VM candidates. First, the paper formulates multi-objective optimization problems for microservice-based large-scale notification system applications and provides the mathematical deployment model. Then, based on the expected workload and required multi-objective criteria, the paper proposes a set of algorithms that provide the Pareto front optimal solution for preselecting a Cloud Service provider's VM type. In the end, the paper presents a case study that demonstrates the use of the proposed technique. © 2022 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

System identification and model comparison for charging and discharging switching of lithium batteries

System identification and model comparison for charging and ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Yan, Weijian Liu, Xiaoping Long, Zhengyang Zhong, Yunsheng Hu, Lingyan Wu, Xiaolong Nanchang University College of Information Engineering Nanchang China Carleton University Department of Systems and Computer Engineering Nanchang China

ISBN: (纸本)9781665465335

The control of the charging and discharging process of the power lithium battery is the key to its efficient operation. However, there are many complex electrochemical reaction processes, so the power lithium battery is difficult to model. In order to study a more suitable modeling method for the charging and discharging process of lithium batteries, this paper uses the model identification method of ARMAX and Hammerstein-Wiener to carry out a data-driven modeling of the relationship between the input current and the open-circuit voltage of the power supply during the charging and discharging process of lithium batteries. Through parameter identification, this paper compares the ability of two lithium battery system identification models to predict the battery voltage response. Through the identification of parameters, this paper compares the ability of two lithium battery system identification models to predict battery voltage response. The results show that this process has certain nonlinear characteristics, the predictive ability of the linear model is insufficient, and the nonlinear model is more suitable for predicting the dynamic behavior of this process, which provides a reference for future health control. © 2022 IEEE.

关键词： Open circuit voltage

来源：评论

学校读者我要写书评

暂无评论

Distributed Spectrum Sensing for IoT Networks: Architecture, Challenges, and Learning

引用

IEEE Internet of Things Magazine 2021年第2期4卷 66-73页

作者： Gharib, Anastassia Ejaz, Waleed Ibnkahla, Mohamed Carleton University Department of Systems and Computer Engineering Canada Lake-head University Department of Electrical Engineering Canada

Spectrum sensing is believed to be a prominent solution to spectrum scarcity caused by the presence of a large number of devices, particularly in Internet of Things (IoT) applications. Providing spectrum access to all of these devices is one of the paramount issues for I systems. Nevertheless, IoT poses several challenges for spectrum sensing that have yet to be overcome. Conventional spectrum sensing techniques have to be carefully modified to be applied to sophisticated and scalable IoT systems. In this paper, an analysis of spectrum sensing for IoT and its possible architecture configurations are presented. We provide an extensive list of challenges associated with spectrum sensing for IoT systems. Focus is given to distributed learning approaches known as incremental, consensus, and diffusion learning in the context of IoT. We further present a case study on cooperative spectrum sensing for IoT systems, where we propose an optimized distributed solution based on diffusion learning. Finally, simulation results demonstrate that the proposed solution improves detection performance and aggregate secondary IoT network throughput, and can minimize hardware complexity for secondary IoT users. © 2018 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Security Patterns for Machine Learning: The Data-Oriented Stages 22

Security Patterns for Machine Learning: The Data-Oriented St...

引用

Proceedings of the 27th European Conference on Pattern Languages of Programs

作者： Xinrui Zhang Jason Jaskolka Systems and Computer Engineering Carleton University Canada

ISBN: (纸本)9781450395946

Security in machine learning (ML) is one of the top priorities in many ML-based systems in the field of healthcare, finance, energy, transportation, and cybersecurity. Since developing ML applications requires multidisciplinary effort, it is important to eliminate knowledge mismatch about security among the team members in the early design phase. In this paper, we present a collection of security patterns for the data-oriented stages in the ML workflow, including data collection, data storage, and data preparation. This provides a concise guidance on how to protect each stage from known threats, as well as a communication vocabulary for different roles to consider security without being security experts.

关键词： data machine learning countermeasures security pattern threats

来源：评论

学校读者我要写书评

暂无评论

Indoor Temporally Constrained Instantaneous Ego-Motion Estimation Using 4-D Doppler Radar

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Lovett, Samuel MacWilliams, Kade Rajan, Sreeraman Rossa, Carlos Carleton University Department of Systems and Computer Engineering OttawaONKIS 5B6 Canada

Indoor ego-motion estimation using millimeter-wave Doppler sensors is challenging due to high levels of outliers, primarily caused by multipath reflections. A standard approach to mitigate these outliers is random sample consensus (RANSAC), where the ego-motion model is derived from data collected at a single time step, overlooking the continuity between successive measurements. In this article, we demonstrate that leveraging temporal relationships across multiple time steps can improve ego-motion estimation accuracy in indoor environments. We introduce two novel RANSAC-based methods that incorporate a weighted sliding window to enhance ego-motion estimation: temporal sample consensus (TEMPSAC) and temporally weighted least squares (TWLSQ). In TEMPSAC, samples are selected with a probability-weighted by their temporal proximity, and the velocity model is generated using least-squares regression (LSQ). In TWLSQ, samples are uniformly selected, but the velocity model is parameterized with a temporally weighted LSQ. Both methods calculate the platform’s motion by prioritizing temporally consistent inliers. Experimental validation of 18 indoor trajectories shows an average position accuracy improvement of 27% compared to previous RANSAC-based ego-motion implementations. The results demonstrate the effectiveness of incorporating temporal information into mmWave-based ego-motion estimation. © 1963-2012 IEEE.

关键词： Doppler radar

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Techniques for Enhancing the Performance of Inter-Cloud Data Transfers

Machine Learning Based Techniques for Enhancing the Performa...

引用

Annual Modeling and Simulation Conference (ANNSIM)

作者： Juan Pablo Contreras Shikharesh Majumdar Ali El-Haraki Department of Systems and Computer Engineering Carleton University Canada Telus Canada

ISBN: (数字)9781713899310

ISBN: (纸本)9798350350562

This paper presents machine learning based techniques to enhance the performance of inter-cloud data transfers. The inter-cloud systems comprise a "compute cloud" for data processing and a "storage cloud" for storing the results of the computation. Real world datasets are used to analyze the performance of a proof-of-concept prototype. For the datasets experimented with, using a recurrent neural network or a transformer network to dynamically buffer data can significantly improve data transfer times in comparison to sending data to the storage cloud without buffering it first. The proposed data transfer techniques, the proof-of-concept prototypes, and the insights into the impact of the system and workload parameters on performance are described.

关键词： Recurrent neural networks Prototypes Machine learning Data transfer Transformers Data models

来源：评论

学校读者我要写书评

暂无评论

Deep Q-Learning-Based Resource Management in IRS-Assisted VLC systems

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2024年 2卷 34-48页

作者： Hammadi, Ahmed Al Bariah, Lina Muhaidat, Sami Al-Qutayri, Mahmoud Sofotasios, Paschalis C. Debbah, Merouane Technology Innovation Institute Abu Dhabi United Arab Emirates Khalifa University Center for Cyber-Physical Systems Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Carleton University Department of Systems and Computer Engineering OttawaK1S 5B6 Canada Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Tampere University Department of Electrical Engineering Tampere33014 Finland Khalifa University KU 6G Center Abu Dhabi United Arab Emirates

Visible Light Communication (VLC) is a promising enabling technology for the next-generation wireless networks, as it complements radio-frequency (RF)-based communications by providing wider bandwidth, higher data rates, and immunity to interference from electromagnetic sources. However, due to its unique characteristics, VLC is highly sensitive to the line-of-sight (LoS) blockage. Recently, intelligent reflecting surface (IRS) has been proposed as an innovative solution that dynamically reconfigures the wireless environment. The present contribution proposes a two-stage resource management framework in an indoor VLC system: In the first stage, a maximum possible fairness (MPF) algorithm is presented in order to maximize the fairness amongst the users. In the second stage, deep Q-learning is exploited in order to maximize the overall spectral efficiency (SE). The corresponding numerical results have shown that the proposed DQL-MPF framework exhibits superior performance in terms of both the overall SE and Jain's Fair Index, achieved at a fast convergence rate. More specifically, when the noise power is high and the number of users is relatively large, the DQL-MPF algorithm achieves a more than tenfold overall SE compared to the Baseline scheme. Moreover, the synergy between the MPF and the DQL algorithms is investigated. To this end, we demonstrate that the MPF algorithm maximizes the fairness amongst the users while the DQL algorithm maximizes the overall SE and improves the robustness against the noise. Our results also highlight the effectiveness of the proposed algorithm in leveraging the increasing number of IRS elements for optimized performance. © 2023 The Authors.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

Computational Offloading for the Industrial Internet of Things: A Performance Analysis 2

Computational Offloading for the Industrial Internet of Thin...

引用

2nd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2022

作者： Bouhoula, Sirine Avgeris, Marios Leivadeas, Aris Lambadaris, Ioannis Department of Software and IT Engineering Montréal Canada Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (数字)9781665498258

ISBN: (纸本)9781665498258

The challenge of minimizing mission response times and the energy consumption of computationally-constrained IoT devices, is becoming increasingly important in Industry 4.0 environments, where mission-critical tasks require real-time and latency-sensitive processing. In this context, the computational offloading paradigm becomes an attractive alternative for utilising remote, computationally capable resources placed at the network Edge, to execute demanding applications. In this paper, an analysis of the main options for task execution (ondevice, Edge and Cloud) is performed, under different sensing and actuation scenarios. These results outline the need of an intelligent decision making mechanism to dynamically alternate between the available execution environments, as a response to the varying networking conditions. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

An Accurate, Low-Parameter and Deployable ML Architecture for Next Location Prediction

An Accurate, Low-Parameter and Deployable ML Architecture fo...

引用

IEEE Future Networks World Forum (FNWF)

作者： Calvin Jary Nafiseh Kahani Systems and Computer Engineering Carleton University Canada

Next location prediction is a discipline that involves predicting a user's next location. Its applications include resource allocation, quality of service, energy efficiency, and traffic man-agement. This paper proposes an energy-efficient, small, and low-parameter machine learning (ML) architecture for accurate next location prediction, deployable on modest base stations and edge devices. To accomplish this we ran a hundred hyperparameter experiments on the full human mobility patterns of an entire city, to determine an exact ML architecture that reached a plateau of accuracy with the least amount of model parameters. We successfully achieved a reduction in the number of model parameters within published ML architectures from 202 million down to 2 million. This reduced the total size of the model parameters from 791 MB down to 8 MB. Additionally, this decreased the training time by a factor of four, the amount of graphics processing unit (GPU) memory needed for training by a factor of twenty, and the overall accuracy was increased from 80.16% to 82.54%. This improvement allows for modest base stations and edge devices which do not have a large amount of memory or storage, to deploy and utilize the proposed ML architecture for next location prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mass Configuration of Heterogeneous IIoT Nodes: A Proposal and Experimental Evaluation

Mass Configuration of Heterogeneous IIoT Nodes: A Proposal a...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Darius Saif Ashraf Matrawy Department of Systems and Computer Engineering Carleton University School of Information Technology

ISBN: (数字)9798350370997

ISBN: (纸本)9798350371000

Securely managing Internet of Things (IoT) devices is a fundamental challenge. Management protocols for IoT must be scalable and extensible, especially when dealing with device heterogeneity. Because of device resource limitations in IoT and the sheer size of such networks, traditional management protocols are not well- suited. In this paper, we propose our HTTP/3 publish-subscribe architecture to meet the ends of en masse device configuration, on-boarding, and monitoring. We compared our solution to industry-standard protocols by collecting data from real traffic in networks of up to 500 clients. We found our solution to excel in ease of use and performance, while having slightly higher CPU utilization compared to the other protocols.

关键词： Performance evaluation Protocols computer architecture Publish-subscribe Containers Market research Proposals

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：